User-profile-based risk assessment method, device, equipment, and storage medium

Abstract

The present invention relates to artificial intelligence technology, and discloses a risk assessment method based on user portrait, including: generating a basic risk portrait according to the user's pre-loan data, and calculating the user's initial risk value according to the basic risk portrait; calculating the user's repayment intention value according to the user's post-loan repayment data; calculating the user's risk adjustment coefficient according to the user's post-loan related product overdue data; querying the user's associated users, obtaining the associated users' historical repayment data, and calculating the user's potential risk coefficient according to the historical repayment data; using the repayment intention value, the risk adjustment coefficient and the potential risk coefficient to numerically adjust the initial risk value to obtain the user's actual risk value. In addition, the present invention also relates to blockchain technology, and the pre-loan data can be stored in the nodes of the blockchain. The present invention also proposes a risk assessment device, electronic device and storage medium based on user portraits. The present invention can improve the accuracy of risk assessment.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a risk assessment method, device, electronic device and computer-readable storage medium based on user portrait. Background Art

[0002] With the advent of a credit society, it is increasingly common for people to use credit consumption (loans) to realize their future intended purchasing plans, resulting in the emergence of more and more loan companies or companies that can provide loan services in the market. However, as people's demand for credit consumption is also increasing, the scale of loans of various companies is also increasing. When the loan amount reaches a certain scale, if the lender is unable to repay the loan in time, the cash flow of the company providing the loan will be interrupted, which will lead to a greater risk of bankruptcy for the company.

[0003] The current assessment methods for user loan risks are mostly line assessments based on pre-loan user data analysis, that is, before providing a loan to a user, the user's relevant information is analyzed to determine the user's loan risk. However, when the user's loan period is long, due to the pre-emptive nature of this method, the pre-assessed loan risk will become increasingly inaccurate over time. Summary of the invention

[0004] The present invention provides a risk assessment method, device and computer-readable storage medium based on user portraits, the main purpose of which is to solve the problem of low accuracy when performing risk assessment.

[0005] To achieve the above object, the present invention provides a risk assessment method based on user portrait, comprising:

[0006] Acquire the user's pre-loan data, generate the user's basic risk profile based on the pre-loan data, and calculate the user's initial risk value based on the basic risk profile;

[0007] Acquiring the post-loan repayment data of the user, and calculating the repayment intention value of the user according to the post-loan repayment data;

[0008] Obtaining the overdue data of post-loan related products of the user, and calculating the risk adjustment coefficient of the user according to the overdue data of post-loan related products;

[0009] Querying the associated users of the user, obtaining the historical repayment data of the associated users, and calculating the potential risk coefficient of the user based on the historical repayment data;

[0010] The initial risk value is numerically adjusted using the repayment intention value, the risk adjustment coefficient and the potential risk coefficient to obtain the actual risk value of the user.

[0011] Optionally, generating a basic risk profile of the user according to the pre-loan data includes:

[0012] Selecting one of the pre-loan data as target data one by one;

[0013] Performing semantic extraction on the target data to obtain data semantics;

[0014] Converting the data semantics of each target data into a semantic vector;

[0015] All semantic vectors are concatenated into the basic risk profile of the user.

[0016] Optionally, performing semantic extraction on the target data to obtain data semantics includes:

[0017] Performing convolution and pooling processing on the target data to obtain low-dimensional feature semantics of the target data;

[0018] Mapping the low-dimensional feature semantics to a pre-constructed high-dimensional space to obtain high-dimensional feature semantics;

[0019] The high-dimensional feature semantics are screened using a preset activation function to obtain data semantics.

[0020] Optionally, the step of splicing all semantic vectors into a basic risk profile of the user includes:

[0021] Counting the vector length of each of the semantic vectors;

[0022] Selecting the semantic vector with the largest vector length as the target vector, and determining the vector length of the target vector as the target length;

[0023] The length of each semantic vector is extended to the target length, and each extended semantic vector is concatenated as a row vector to obtain a basic risk profile of the user.

[0024] Optionally, calculating the user's repayment intention value according to the post-loan repayment data includes:

[0025] Obtain the number of repayment periods and the total loan amount of the user;

[0026] Counting the number of on-time repayments of the user based on the post-loan repayment data, and counting the amount of repayments of the user based on the post-loan repayment data;

[0027] Dividing the amount of the repaid amount by the total loan amount to obtain a first intention degree;

[0028] The second intention degree is obtained by dividing the number of on-time repayments by the number of repayment periods;

[0029] The first intention degree and the second intention degree are weighted and summed using a preset weight coefficient to obtain a repayment intention value.

[0030] Optionally, the step of calculating the risk adjustment coefficient of the user based on the overdue data of the post-loan related products includes:

[0031] Count the total number of products and the number of overdue products in the overdue data of the post-loan related products;

[0032] The risk adjustment coefficient of the user is obtained by dividing the number of overdue products by the total number of products.

[0033] Optionally, calculating the potential risk factor of the user according to the historical repayment data includes:

[0034] Counting the total number of the associated users, and counting the number of overdue users with overdue repayments in the historical repayment data;

[0035] The difference between the total number of users and the number of overdue users is calculated, the difference is divided by the total number of users, and the square root of the result of the division is calculated to obtain the potential risk coefficient.

[0036] In order to solve the above problems, the present invention also provides a risk assessment device based on user portrait, the device comprising:

[0037] A profile generation module is used to obtain the user's pre-loan data, generate the user's basic risk profile based on the pre-loan data, and calculate the user's initial risk value based on the basic risk profile;

[0038] An intention value analysis module, used to obtain the post-loan repayment data of the user, and calculate the repayment intention value of the user based on the post-loan repayment data;

[0039] An adjustment coefficient calculation module, used to obtain the overdue data of post-loan related products of the user, and calculate the risk adjustment coefficient of the user according to the overdue data of post-loan related products;

[0040] A potential coefficient analysis module, used to query the associated users of the user, obtain the historical repayment data of the associated users, and calculate the potential risk coefficient of the user based on the historical repayment data;

[0041] The risk assessment module is used to numerically adjust the initial risk value using the repayment intention value, the risk adjustment coefficient and the potential risk coefficient to obtain the actual risk value of the user.

[0042] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0043] at least one processor; and,

[0044] a memory communicatively connected to the at least one processor; wherein,

[0045] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the risk assessment method based on user portrait described above.

[0046] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the above-mentioned risk assessment method based on user portrait.

[0047] The embodiment of the present invention can generate a basic risk profile using the user's pre-loan data, and calculate the user's initial risk value based on the profile. At the same time, based on the user's various post-loan data, calculate post-loan risk indicators such as repayment intention value, risk adjustment coefficient and potential risk coefficient, and adjust the initial risk value numerically according to the calculated post-loan risk indicators, thereby improving the accuracy of risk assessment for the user. Therefore, the risk assessment method, device, electronic device and computer-readable storage medium based on user profile proposed in the present invention can solve the problem of low accuracy when performing risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A schematic diagram of a process flow of a risk assessment method based on user portraits provided in one embodiment of the present invention;

[0049] Figure 2 A schematic diagram of a process for generating a basic risk profile of a user provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of a process for calculating a user's repayment intention value provided by an embodiment of the present invention;

[0051] Figure 4 A functional module diagram of a risk assessment device based on user portrait provided by an embodiment of the present invention;

[0052] Figure 5 A schematic diagram of the structure of an electronic device for implementing the risk assessment method based on user portrait provided in one embodiment of the present invention.

[0053] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0055] The embodiment of the present application provides a risk assessment method based on user portrait. The execution subject of the risk assessment method based on user portrait includes but is not limited to at least one of the electronic devices such as the server, the terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the risk assessment method based on user portrait can be executed by software or hardware installed on the terminal device or the server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0056] Reference Figure 1 FIG. 1 is a flow chart of a risk assessment method based on user portrait provided by an embodiment of the present invention. In this embodiment, the risk assessment method based on user portrait includes:

[0057] S1. Obtain the user's pre-loan data, generate the user's basic risk profile based on the pre-loan data, and calculate the user's initial risk value based on the basic risk profile.

[0058] In the embodiment of the present invention, the pre-loan data refers to the user's age, occupation, income status, number of historical loans, historical loan amount, number of historical overdue payments, and other data before the loan company provides the loan to the user.

[0059] In detail, computer statements with data capture functions (such as Java statements, Python statements, etc.) can be used to capture pre-loan data that the user authorizes to be obtained from a predetermined storage area, where the storage area includes but is not limited to a database, a blockchain node, and a network cache.

[0060] Specifically, the pre-loan data includes various data of the user, which shows the various behaviors of the user before the loan. Therefore, the pre-loan data can be used to generate the basic risk profile of the user, and the initial risk value of the user can be calculated based on the basic risk profile to facilitate the subsequent risk assessment of the user.

[0061] In the embodiment of the present invention, Figure 2 As shown, generating the basic risk profile of the user based on the pre-loan data includes:

[0062] S21, selecting one of the pre-loan data as target data one by one;

[0063] S22, performing semantic extraction on the target data to obtain data semantics;

[0064] S23, converting the data semantics of each target data into a semantic vector;

[0065] S24. Concatenate all semantic vectors into a basic risk profile of the user.

[0066] In the embodiment of the present invention, the target data may be selected from the pre-loan data in sequence, or the target data may be selected from the pre-loan data randomly without replacement.

[0067] In the embodiment of the present invention, a pre-constructed semantic analysis model may be used to perform semantic extraction on the target data to obtain data semantics.

[0068] In detail, the semantic analysis model includes but is not limited to an NLP (Natural Language Processing) model and an HMM (Hidden Markov Model).

[0069] For example, a pre-built semantic analysis model is used to perform convolution, pooling and other operations on the target data to extract a low-dimensional feature expression of the target data, and then the extracted low-dimensional feature expression is mapped to a pre-built high-dimensional space to obtain a high-dimensional feature expression of the low-dimensional feature, and a preset activation function is used to selectively output the high-dimensional feature expression to obtain data semantics.

[0070] In the embodiment of the present invention, the step of performing semantic extraction on the target data to obtain data semantics includes:

[0071] Performing convolution and pooling processing on the target data to obtain low-dimensional feature semantics of the target data;

[0072] Mapping the low-dimensional feature semantics to a pre-constructed high-dimensional space to obtain high-dimensional feature semantics;

[0073] The high-dimensional feature semantics are screened using a preset activation function to obtain data semantics.

[0074] In detail, the target data can be convolved and pooled through a semantic analysis model to reduce the data dimension of the target data, thereby reducing the computing resources occupied when analyzing the target data and improving the efficiency of semantic extraction.

[0075] Specifically, a preset mapping function may be used to map low-dimensional feature semantics to a pre-constructed high-dimensional space, wherein the mapping function includes a Gaussian Radial Basis Function function and a Gaussian function in a MATLAB library.

[0076] For example, if the low-dimensional feature semantics is a point in a two-dimensional plane, the two-dimensional coordinates of the point in the two-dimensional plane can be calculated using a mapping function to convert the two-dimensional coordinates into three-dimensional coordinates, and the calculated three-dimensional coordinates can be used to map the point to a pre-constructed three-dimensional space to obtain the high-dimensional feature semantics of the low-dimensional feature semantics.

[0077] Mapping the low-dimensional feature semantics to a pre-constructed high-dimensional space can improve the classifiability of the low-dimensional features, thereby improving the accuracy of data semantics obtained by screening features from the obtained high-dimensional feature semantics.

[0078] In an embodiment of the present invention, a preset activation function can be used to calculate the output value of each feature semantics in the high-dimensional feature semantics, and the feature semantics whose output value is greater than a preset output threshold is selected as the data semantics. The activation function includes but is not limited to a sigmoid activation function, a tanh activation function, and a relu activation function.

[0079] For example, there are feature semantics A, feature semantics B and feature semantics C in the high-dimensional feature semantics. The activation function is used to calculate feature semantics A, feature semantics B and feature semantics C respectively, and the output value of feature semantics A is 80, the output value of feature semantics B is 30, and the output value of feature semantics C is 70. When the output threshold is 50, feature semantics A and feature semantics C are output as the data semantics of the target product.

[0080] In an embodiment of the present invention, the data semantics may be vectorized by a preset vector transformation model to obtain a semantic vector. The vector transformation model includes but is not limited to a word2vec model and a Bert model.

[0081] In an embodiment of the present invention, after obtaining the semantic vector, all the semantic vectors may be concatenated to generate a basic risk profile.

[0082] In the embodiment of the present invention, the step of splicing all semantic vectors into the basic risk profile of the user includes:

[0083] Counting the vector length of each of the semantic vectors;

[0084] Selecting the semantic vector with the largest vector length as the target vector, and determining the vector length of the target vector as the target length;

[0085] The length of each semantic vector is extended to the target length, and each extended semantic vector is concatenated as a row vector to obtain a basic risk profile of the user.

[0086] In detail, since the length of each of the semantic vectors may be different, in order to perform vector concatenation on the semantic vectors, the vector lengths of the semantic vectors need to be unified.

[0087] In the embodiment of the present invention, the length of each semantic vector is counted, and vectors with shorter lengths are extended so that the lengths of all semantic vectors are the same.

[0088] For example, there is a first semantic vector [11, 36, 22] and a second semantic vector [14, 25, 31, 27] in the semantic vector. Statistics show that the length of the first vector of the first semantic vector is 3, and the length of the second vector of the second semantic vector is 4. The length of the second vector is greater than the length of the first vector. In this case, the first semantic vector can be extended using preset parameters (such as 0) until the length of the first vector is equal to the length of the second vector, thereby obtaining the extended first semantic vector [11, 36, 22, 0].

[0089] In the embodiment of the present invention, the two vectors may be merged in the column dimension by adding corresponding column elements in the two vectors.

[0090] For example, if there is a first semantic vector [11, 36, 22, 0] and a second semantic vector [14, 25, 31, 27], the elements of the corresponding columns in the first semantic vector and the second semantic vector can be added to obtain the basic risk portrait [25, 61, 53, 27].

[0091] In another embodiment of the present invention, the corresponding column elements in the two vectors may be displayed in parallel to generate a matrix using the two vectors, thereby achieving column dimension merging between the vectors.

[0092] For example, if the first semantic vector is [11, 36, 22, 0] and the second semantic vector is [14, 25, 31, 27], the elements of the corresponding columns in the first semantic vector and the second semantic vector can be displayed in parallel to obtain a matrix And use this matrix as the basic risk profile of the user.

[0093] Furthermore, the basic risk profile is a matrix obtained by concatenating multiple vectors, so the value of the basic risk profile can be directly calculated to obtain the initial risk value of the user.

[0094] S2. Obtain the post-loan repayment data of the user, and calculate the repayment intention value of the user based on the post-loan repayment data.

[0095] In one of the practical application scenarios of the present invention, since the initial risk value is generated based on the user's pre-loan data, the initial risk value can only represent the user's pre-loan risk, but cannot accurately represent the user's post-loan repayment risk. Therefore, the user's post-loan repayment data can be obtained to analyze the user's repayment behavior based on the user's repayment data, thereby realizing the assessment of post-loan risk and improving the timeliness and accuracy of subsequent assessments of user risk values.

[0096] In the embodiment of the present invention, the post-loan repayment data refers to the repayment amount, repayment time and other data of the user within each repayment period after the loan.

[0097] In detail, the step of obtaining the post-loan repayment data of the user is consistent with the step of obtaining the pre-loan data of the user in S1, and will not be repeated here.

[0098] Furthermore, the post-loan repayment data may be analyzed to calculate the user's repayment intention value, wherein the repayment intention value is used to identify the user's intention to repay on time.

[0099] In the embodiment of the present invention, Figure 3 As shown, the calculation of the user's repayment intention value based on the post-loan repayment data includes:

[0100] S31, obtaining the repayment period and total loan amount of the user;

[0101] S32, counting the number of on-time repayments of the user according to the post-loan repayment data, and counting the amount of repayments of the user according to the post-loan repayment data;

[0102] S33, dividing the amount of the repaid amount by the total loan amount to obtain a first intention degree;

[0103] S34, dividing the number of on-time repayments by the number of repayment periods to obtain a second intention degree;

[0104] S35. Using a preset weight coefficient, perform weighted summation on the first intention degree and the second intention degree to obtain a repayment intention value.

[0105] In detail, the repayment period refers to the number of installments for the user's loan repayment, and the total loan amount refers to the total amount of the user's loan.

[0106] Specifically, the post-loan repayment data may be counted to determine the number of on-time repayments made by the user within the number of periods already repaid, as well as the total amount of money already repaid by the user.

[0107] In the embodiment of the present invention, the calculation of the user's repayment intention according to the number of repayment periods, the total loan amount, the number of on-time repayments and the amount of repaid money includes:

[0108] The repayment intention degree is calculated using the following weight algorithm:

[0109]

[0110] Among them, Y is the repayment intention, A is the amount of the repaid amount, B is the total loan amount, C is the number of repayments on time, D is the number of repayment periods, and α and β are preset weight coefficients.

[0111] S3. Obtain the overdue data of post-loan related products of the user, and calculate the risk adjustment coefficient of the user according to the overdue data of post-loan related products.

[0112] In the embodiment of the present invention, the expected data of post-loan related products refers to the overdue status data of other loan products held by the user after the user obtains the loan but has not repaid the loan.

[0113] Specifically, when a user holds multiple loan products, if other loan products are overdue, the user will also have a large overdue behavior on this loan.

[0114] Specifically, the step of obtaining the overdue data of the user's post-loan related products is consistent with the step of obtaining the user's pre-loan data in S1, and will not be repeated here.

[0115] In the embodiment of the present invention, the step of calculating the risk adjustment coefficient of the user based on the overdue data of the post-loan related products includes:

[0116] Count the total number of products and the number of overdue products in the overdue data of the post-loan related products;

[0117] The risk adjustment coefficient of the user is obtained by dividing the number of overdue products by the total number of products.

[0118] In detail, the method of obtaining the risk adjustment coefficient of the user by dividing the number of overdue products by the total number of products includes:

[0119] The risk adjustment factor of the user is obtained by dividing the number of overdue products by the total number of products using the following formula:

[0120]

[0121] Wherein, X is the risk adjustment coefficient, E is the number of overdue products, and F is the total number of products.

[0122] S4. Query the associated users of the user, obtain the historical repayment data of the associated users, and calculate the potential risk coefficient of the user according to the historical repayment data.

[0123] In one of the practical application scenarios of the present invention, it can be considered that there is a certain potential connection between the habits and repayment ability of each person in the group to which the user belongs. For example, when a large number of associated users have loan overdue records among multiple associated users who have an associated relationship with the user, the possibility of loan overdue for the user may be higher.

[0124] Therefore, the associated users of the user can be queried, and the historical repayment data of the associated users can be obtained, and then the historical repayment data can be analyzed to obtain the potential risk factor of the user using the historical repayment data of the associated users, wherein the historical repayment data refers to the loan records, overdue repayment records and other data of each associated user among the associated users who have an associated relationship with the user.

[0125] In the embodiment of the present invention, a pre-built associated user table can be obtained, and an index of the associated user table can be created using the CREATE INDEX function in the SQL library, and then the associated users of the user can be queried from the associated user table according to the index, wherein the associated user table contains multiple users and the association relationship between each user.

[0126] In detail, the step of obtaining the historical repayment data of the associated user is consistent with the step of obtaining the user's pre-loan data in S1, and will not be repeated here.

[0127] In the embodiment of the present invention, the step of calculating the potential risk coefficient of the user according to the historical repayment data includes:

[0128] Counting the total number of the associated users, and counting the number of overdue users with overdue repayments in the historical repayment data;

[0129] The difference between the total number of users and the number of overdue users is calculated, the difference is divided by the total number of users, and the square root of the result of the division is calculated to obtain the potential risk coefficient.

[0130] In detail, the calculating the difference between the total number of users and the number of overdue users, dividing the difference by the total number of users, and calculating the square root of the result of the division to obtain the potential risk coefficient includes:

[0131] The potential risk factor of the user is calculated according to the total number of users and the number of overdue users using the following formula:

[0132]

[0133] Wherein, Z is the potential risk coefficient, G is the total number of users, and H is the number of overdue users.

[0134] S5. Use the repayment intention value, the risk adjustment coefficient and the potential risk coefficient to numerically adjust the initial risk value to obtain the actual risk value of the user.

[0135] In the embodiment of the present invention, since the initial risk value can only represent the risk of the user before the loan, but cannot accurately represent the risk of the user repaying the loan after the loan, in order to improve the accuracy of the analysis of the risk value of the user, the indicators obtained from the post-loan data analysis, such as the repayment intention value, the risk adjustment coefficient and the potential risk coefficient, can be used to adjust the initial risk value numerically to improve the accuracy of the risk assessment of the user.

[0136] In the embodiment of the present invention, the method of numerically adjusting the initial risk value by using the repayment intention value, the risk adjustment coefficient and the potential risk coefficient to obtain the actual risk value of the user includes:

[0137] The initial risk value is numerically adjusted using the following numerical adjustment algorithm to obtain the actual risk value of the user:

[0138] S=(X+Y+Z)*Q

[0139] Among them, S is the actual risk value, Q is the initial risk value, X is the risk adjustment coefficient, Y is the repayment intention degree, and Z is the potential risk coefficient.

[0140] The embodiment of the present invention can generate a basic risk profile using the user's pre-loan data, and calculate the user's initial risk value based on the profile. At the same time, based on the user's various post-loan data, calculate post-loan risk indicators such as repayment intention value, risk adjustment coefficient and potential risk coefficient, and adjust the initial risk value numerically based on the calculated post-loan risk indicators, thereby improving the accuracy of risk assessment for the user. Therefore, the risk assessment method based on user profile proposed by the present invention can solve the problem of low accuracy when performing risk assessment.

[0141] like Figure 4 , which is a functional module diagram of a risk assessment device based on user portrait provided by an embodiment of the present invention.

[0142] The risk assessment device 100 based on user portrait of the present invention can be installed in an electronic device. According to the functions to be implemented, the risk assessment device 100 based on user portrait can include a portrait generation module 101, an intention value analysis module 102, an adjustment coefficient calculation module 103, a potential coefficient analysis module 104 and a risk assessment module 105. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0143] In this embodiment, the functions of each module / unit are as follows:

[0144] The profile generation module 101 is used to obtain the user's pre-loan data, generate the user's basic risk profile based on the pre-loan data, and calculate the user's initial risk value based on the basic risk profile;

[0145] The intention value analysis module 102 is used to obtain the post-loan repayment data of the user and calculate the repayment intention value of the user according to the post-loan repayment data;

[0146] The adjustment coefficient calculation module 103 is used to obtain the overdue data of the post-loan related products of the user, and calculate the risk adjustment coefficient of the user according to the overdue data of the post-loan related products;

[0147] The potential coefficient analysis module 104 is used to query the associated users of the user, obtain the historical repayment data of the associated users, and calculate the potential risk coefficient of the user based on the historical repayment data;

[0148] The risk assessment module 105 is used to numerically adjust the initial risk value using the repayment intention value, the risk adjustment coefficient and the potential risk coefficient to obtain the actual risk value of the user.

[0149] In detail, each module described in the risk assessment device 100 based on user portrait in the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The risk assessment method based on user portraits is similar to the technical means described in the previous section and can produce the same technical effects, so I will not go into details here.

[0150] like Figure 5 , is a schematic diagram of the structure of an electronic device for implementing a risk assessment method based on user portraits provided by an embodiment of the present invention.

[0151] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a risk assessment program based on a user portrait.

[0152] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes the programs or modules stored in the memory 11 (for example, executing a risk assessment program based on user portraits, etc.), and calls the data stored in the memory 11 to execute various functions of the electronic device and process data.

[0153] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as the code of a risk assessment program based on a user portrait, but also can be used to temporarily store data that has been output or is to be output.

[0154] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0155] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0156] Figure 5 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0157] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0158] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0159] The user portrait-based risk assessment program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0160] Acquire the user's pre-loan data, generate the user's basic risk profile based on the pre-loan data, and calculate the user's initial risk value based on the basic risk profile;

[0161] Acquiring the post-loan repayment data of the user, and calculating the repayment intention value of the user according to the post-loan repayment data;

[0162] Obtaining the overdue data of post-loan related products of the user, and calculating the risk adjustment coefficient of the user according to the overdue data of post-loan related products;

[0163] Querying the associated users of the user, obtaining the historical repayment data of the associated users, and calculating the potential risk coefficient of the user based on the historical repayment data;

[0164] The initial risk value is numerically adjusted using the repayment intention value, the risk adjustment coefficient and the potential risk coefficient to obtain the actual risk value of the user.

[0165] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0166] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0167] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0168] Acquire the user's pre-loan data, generate the user's basic risk profile based on the pre-loan data, and calculate the user's initial risk value based on the basic risk profile;

[0169] Acquiring the post-loan repayment data of the user, and calculating the repayment intention value of the user according to the post-loan repayment data;

[0170] Obtaining the overdue data of post-loan related products of the user, and calculating the risk adjustment coefficient of the user according to the overdue data of post-loan related products;

[0171] Querying the associated users of the user, obtaining the historical repayment data of the associated users, and calculating the potential risk coefficient of the user based on the historical repayment data;

[0172] The initial risk value is numerically adjusted using the repayment intention value, the risk adjustment coefficient and the potential risk coefficient to obtain the actual risk value of the user.

[0173] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0174] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0175] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0176] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0177] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0178] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0179] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0180] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A risk assessment method based on user portrait, characterized in that: The method comprises: Acquire the user's pre-loan data, generate the user's basic risk profile based on the pre-loan data, and calculate the user's initial risk value based on the basic risk profile; Acquiring the post-loan repayment data of the user, and calculating the repayment intention value of the user according to the post-loan repayment data; Obtaining the overdue data of post-loan related products of the user, and calculating the risk adjustment coefficient of the user according to the overdue data of post-loan related products; Querying the associated users of the user, obtaining the historical repayment data of the associated users, and calculating the potential risk coefficient of the user based on the historical repayment data; Using the repayment intention value, the risk adjustment coefficient and the potential risk coefficient, the initial risk value is numerically adjusted to obtain the actual risk value of the user; The generating of the basic risk profile of the user according to the pre-loan data includes: selecting one of the data from the pre-loan data as the target data one by one; performing semantic extraction on the target data to obtain data semantics; converting the data semantics of each of the target data into a semantic vector; and splicing all the semantic vectors into the basic risk profile of the user; The step of splicing all the semantic vectors into the basic risk profile of the user includes: counting the vector length of each of the semantic vectors; selecting the semantic vector with the largest vector length as the target vector, and determining the vector length of the target vector as the target length; extending the length of each semantic vector to the target length, and splicing each extended semantic vector as a row vector to obtain the basic risk profile of the user; The method of calculating the user's repayment intention value based on the post-loan repayment data includes: obtaining the number of repayment periods and the total loan amount of the user; counting the number of on-time repayments of the user based on the post-loan repayment data, and counting the amount of repaid funds of the user based on the post-loan repayment data; dividing the amount of repaid funds by the total loan amount to obtain a first intention degree; dividing the number of on-time repayments by the number of repayment periods to obtain a second intention degree; and weighted summing the first intention degree and the second intention degree using a preset weight coefficient to obtain a repayment intention value.

2. The risk assessment method based on user portrait according to claim 1, characterized in that: The performing semantic extraction on the target data to obtain data semantics includes: Performing convolution and pooling processing on the target data to obtain low-dimensional feature semantics of the target data; Mapping the low-dimensional feature semantics to a pre-constructed high-dimensional space to obtain high-dimensional feature semantics; The high-dimensional feature semantics are screened using a preset activation function to obtain data semantics.

3. The risk assessment method based on user portrait according to claim 1, characterized in that: The calculating of the risk adjustment coefficient of the user according to the overdue data of the post-loan related products includes: Count the total number of products and the number of overdue products in the overdue data of the post-loan related products; The risk adjustment coefficient of the user is obtained by dividing the number of overdue products by the total number of products.

4. The risk assessment method based on user portrait according to any one of claims 1 to 3, characterized in that: The calculating the potential risk factor of the user according to the historical repayment data includes: Counting the total number of the associated users, and counting the number of overdue users with overdue repayments in the historical repayment data; The difference between the total number of users and the number of overdue users is calculated, the difference is divided by the total number of users, and the square root of the result of the division is calculated to obtain the potential risk coefficient.

5. A risk assessment device based on user portrait, used to implement the risk assessment method based on user portrait as claimed in any one of claims 1 to 4, characterized in that: The device comprises: A profile generation module is used to obtain the user's pre-loan data, generate the user's basic risk profile based on the pre-loan data, and calculate the user's initial risk value based on the basic risk profile; An intention value analysis module, used to obtain the post-loan repayment data of the user, and calculate the repayment intention value of the user based on the post-loan repayment data; An adjustment coefficient calculation module, used to obtain the overdue data of post-loan related products of the user, and calculate the risk adjustment coefficient of the user according to the overdue data of post-loan related products; A potential coefficient analysis module, used to query the associated users of the user, obtain the historical repayment data of the associated users, and calculate the potential risk coefficient of the user based on the historical repayment data; The risk assessment module is used to numerically adjust the initial risk value using the repayment intention value, the risk adjustment coefficient and the potential risk coefficient to obtain the actual risk value of the user.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the user portrait-based risk assessment method as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the user portrait-based risk assessment method as described in any one of claims 1 to 4 is implemented.

Images